Hugging Face's logo

UCLNLP
/
monoweb

Safetensors
pretraining
multilingual
language-model
Model card Files
xet
 Community
yaolu commited on
Commit
431cb71
·
verified ·
1 Parent(s): 13f24c6

Upload model checkpoint

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. ckpt_exp_en_es_onlyparallel/iter_0000500/mp_rank_00/distrib_optim.pt +3 -0
  2. ckpt_exp_en_es_onlyparallel/iter_0000500/mp_rank_00/model_optim_rng.pt +3 -0
  3. ckpt_exp_en_es_onlyparallel/iter_0001000/mp_rank_00/distrib_optim.pt +3 -0
  4. ckpt_exp_en_es_onlyparallel/iter_0001000/mp_rank_00/model_optim_rng.pt +3 -0
  5. ckpt_exp_en_es_onlyparallel/iter_0001500/mp_rank_00/distrib_optim.pt +3 -0
  6. ckpt_exp_en_es_onlyparallel/iter_0001500/mp_rank_00/model_optim_rng.pt +3 -0
  7. ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/config.json +29 -0
  8. ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/generation_config.json +6 -0
  9. ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/model.safetensors +3 -0
  10. ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/special_tokens_map.json +23 -0
  11. ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/tokenizer.json +0 -0
  12. ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/tokenizer.model +3 -0
  13. ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/tokenizer_config.json +43 -0
  14. ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/config.json +29 -0
  15. ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/generation_config.json +6 -0
  16. ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/model.safetensors +3 -0
  17. ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/special_tokens_map.json +23 -0
  18. ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/tokenizer.json +0 -0
  19. ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/tokenizer.model +3 -0
  20. ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/tokenizer_config.json +43 -0
  21. ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/config.json +29 -0
  22. ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/generation_config.json +6 -0
  23. ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/model.safetensors +3 -0
  24. ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/special_tokens_map.json +23 -0
  25. ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/tokenizer.json +0 -0
  26. ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/tokenizer.model +3 -0
  27. ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/tokenizer_config.json +43 -0
  28. ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/config.json +29 -0
  29. ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/generation_config.json +6 -0
  30. ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/model.safetensors +3 -0
  31. ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/special_tokens_map.json +23 -0
  32. ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/tokenizer.json +0 -0
  33. ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/tokenizer.model +3 -0
  34. ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/tokenizer_config.json +43 -0
  35. ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/config.json +29 -0
  36. ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/generation_config.json +6 -0
  37. ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/model.safetensors +3 -0
  38. ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/special_tokens_map.json +23 -0
  39. ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/tokenizer.json +0 -0
  40. ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/tokenizer.model +3 -0
  41. ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/tokenizer_config.json +43 -0
  42. ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/config.json +29 -0
  43. ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/generation_config.json +6 -0
  44. ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/model.safetensors +3 -0
  45. ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/special_tokens_map.json +23 -0
  46. ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/tokenizer.json +0 -0
  47. ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/tokenizer.model +3 -0
  48. ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/tokenizer_config.json +43 -0
  49. ckpt_exp_en_es_onlyparallel/iter_0014000/hf_model/config.json +29 -0
  50. ckpt_exp_en_es_onlyparallel/iter_0014000/hf_model/generation_config.json +6 -0
ckpt_exp_en_es_onlyparallel/iter_0000500/mp_rank_00/distrib_optim.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d81870bf7257c389e44ef6db46da803652ca595a6922f821d77b89d21ee20fc
3
+ size 16145082282
ckpt_exp_en_es_onlyparallel/iter_0000500/mp_rank_00/model_optim_rng.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73fe061c6a183345ea85ea51a81c2960106cee9561b6409808f72baab709c06a
3
+ size 2690946422
ckpt_exp_en_es_onlyparallel/iter_0001000/mp_rank_00/distrib_optim.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90bd67ddcd70d29fc709270d9d181630ebe06a8f1f13b1cdd2f87e0e12a245b
3
+ size 16145082282
ckpt_exp_en_es_onlyparallel/iter_0001000/mp_rank_00/model_optim_rng.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c593a69ea251268e8f389a9ef90019f84cfee8d2e354d57051ba3f3fc43bbe2
3
+ size 2690946422
ckpt_exp_en_es_onlyparallel/iter_0001500/mp_rank_00/distrib_optim.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff57e02d885f2d4ed3a7280e15da8791bf2524d3ffc4667b3c44ac18ac955fa
3
+ size 16145082282
ckpt_exp_en_es_onlyparallel/iter_0001500/mp_rank_00/model_optim_rng.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858fc4d40f9ba703b479e69eae7338638db9967e91fdcb47cf7e7800bb098980
3
+ size 2690946422
ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.52.4"
6
+ }
ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95c2e45a92fd8c40a9f79a5b0b4b946ad8ec80372e32558a02a683ece1781aa
3
+ size 2690871976
ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
ckpt_exp_en_es_onlyparallel/iter_0002000/hf_model/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": null,
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.52.4"
6
+ }
ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:318232ac69fead518832ce948767d61a21b212cd07a45510d5a070297d893298
3
+ size 2690871976
ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
ckpt_exp_en_es_onlyparallel/iter_0004000/hf_model/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": null,
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.52.4"
6
+ }
ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e888707febc5eb92aa87e06c5de5774473b6619a5dc86932f583484c633ccda
3
+ size 2690871976
ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
ckpt_exp_en_es_onlyparallel/iter_0006000/hf_model/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": null,
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.52.4"
6
+ }
ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab7b7fb14a8b1eb783b1375df2d5591aca84e4633bf2591fcfbe6552bfd825a
3
+ size 2690871976
ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
ckpt_exp_en_es_onlyparallel/iter_0008000/hf_model/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": null,
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.52.4"
6
+ }
ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fc1cf9aac9b9a2a1a140358b61b6b056e2f367368f6a5019853aece0bcd1c3
3
+ size 2690871976
ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
ckpt_exp_en_es_onlyparallel/iter_0010000/hf_model/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": null,
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.52.4"
6
+ }
ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67bac19258fc44b62a1622b32fb58b94424123bc4f85d476d7c8b062fe9a665a
3
+ size 2690871976
ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
ckpt_exp_en_es_onlyparallel/iter_0012000/hf_model/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "extra_special_tokens": {},
35
+ "legacy": false,
36
+ "model_max_length": 2048,
37
+ "pad_token": null,
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
ckpt_exp_en_es_onlyparallel/iter_0014000/hf_model/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5504,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
ckpt_exp_en_es_onlyparallel/iter_0014000/hf_model/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.52.4"
6
+ }